The Agent Skills Directory

[SAFE]: The skill provides a procedural framework for managing software development tasks through critical review and execution phases.\n- [SAFE]: It incorporates strong safety guidelines, instructing the agent to stop immediately and seek human clarification when encountering blockers, gaps, or failed verifications.\n- [SAFE]: Implements a principle of least privilege for branch management by requiring explicit user consent before performing any work on the main or master branches.\n- [SAFE]: Although the skill ingests external plan files (a potential surface for indirect prompt injection), the risk is mitigated by mandatory critical review steps and is central to the intended primary purpose of the tool.\n- [SAFE]: No malicious patterns, such as data exfiltration, obfuscation, or unauthorized remote code execution, were detected.

executing-plans